Dynamic Mutation Strategy Selection in Differential Evolution Using Perturbed Adaptive Pursuit

Abstract Diverse mutant vectors play a significant role in the performance of the Differential Evolution (DE). A mutant vector is generated using a stochastic mathematical equation, known as mutation strategy. Many mutation strategies have been proposed in the literature. Utilizing multiple mutation strategies with the help of an adaptive operator selection (AOS) technique can improve the quality of the mutant vector. In this research, one popular AOS technique known as perturbation adaptive pursuit (PAP) is integrated with the DE algorithm for managing a pool of mutation strategies. A community-based reward criterion is proposed that rewards the cumulative performance of the whole population. The proposed approach is called ‘ Dynamic Mutation Strategy Selection in Differential Evolution using Perturbed Adaptive Pursuit (dmss-DE-pap) ’. The performance of dmss-DE-pap is evaluated over the 30D and 50D optimization problems of the CEC 2014 benchmark test suite. Results are competitive when compared with other state-of-the-art evolutionary algorithms and some recent DE variants.